@su-record/vibe 2.7.18 → 2.7.20

package/skills/seo-checklist/SKILL.md

@@ -1,57 +1,57 @@
----
-name: seo-checklist
-description: "SEO gotchas for web development - easy-to-miss items that hurt search ranking"
-triggers: [seo, search, meta, sitemap, schema, structured data, og, opengraph, google, naver]
-priority: 65
----
-
-# SEO Checklist
-
-## Pre-check (K1)
-
-> Is this a public-facing web page that needs search visibility? Internal tools, admin panels, and authenticated-only pages don't need SEO optimization.
-
-## Easy-to-Miss Gotchas
-
-### Meta & Social
-
-| Gotcha | Why It Hurts | Fix |
-|--------|-------------|-----|
-| Missing `<link rel="canonical">` | Duplicate content penalty from URL variants | Set canonical on every page, including paginated |
-| OG image wrong size | Cropped/pixelated on social share | Must be exactly **1200x630px** |
-| Same title/description on all pages | Google treats as duplicate content | Unique title (50-60 chars) + description (150-160 chars) per page |
-| Missing `og:type` | Defaults to "website" for articles | Set `article` for posts, `product` for products |
-
-### Technical
-
-| Gotcha | Why It Hurts | Fix |
-|--------|-------------|-----|
-| `robots.txt` blocks important pages | Pages not indexed | `Allow: /` for public, only block `/api/`, `/admin/` |
-| No sitemap or stale sitemap | Crawler misses new pages | Auto-generate, include `<lastmod>` with real dates |
-| `noindex` left in production | Entire site invisible | Verify `<meta name="robots">` in production build |
-| Images without `width`/`height` | CLS layout shift penalty | Always set dimensions + `loading="lazy"` for below-fold |
-
-### Core Web Vitals
-
-| Metric | Target | Common Miss |
-|--------|--------|-------------|
-| LCP | ≤2.5s | Hero image not preloaded — add `<link rel="preload">` |
-| INP | ≤200ms | Heavy JS on interaction — defer non-critical scripts |
-| CLS | ≤0.1 | Dynamic content without reserved space — set `min-height` |
-
-### Structured Data
-
-| Gotcha | Fix |
-|--------|-----|
-| JSON-LD not validated | Test with Google Rich Results Test before deploy |
-| Wrong `@type` | `Product` for products, `Article` for posts, `FAQPage` for FAQs |
-| Missing `BreadcrumbList` | Add breadcrumb schema for all non-root pages |
-
-## Done Criteria (K4)
-
-- [ ] Every page has unique title, description, canonical URL
-- [ ] OG images are 1200x630px on all shareable pages
-- [ ] `robots.txt` and `sitemap.xml` present and correct
-- [ ] Structured data validates in Rich Results Test
-- [ ] Core Web Vitals green (LCP ≤2.5s, INP ≤200ms, CLS ≤0.1)
-- [ ] No `noindex` tags in production
+---
+name: seo-checklist
+description: "SEO gotchas for web development - easy-to-miss items that hurt search ranking"
+triggers: [seo, search, meta, sitemap, schema, structured data, og, opengraph, google, naver]
+priority: 65
+---
+
+# SEO Checklist
+
+## Pre-check (K1)
+
+> Is this a public-facing web page that needs search visibility? Internal tools, admin panels, and authenticated-only pages don't need SEO optimization.
+
+## Easy-to-Miss Gotchas
+
+### Meta & Social
+
+| Gotcha | Why It Hurts | Fix |
+|--------|-------------|-----|
+| Missing `<link rel="canonical">` | Duplicate content penalty from URL variants | Set canonical on every page, including paginated |
+| OG image wrong size | Cropped/pixelated on social share | Must be exactly **1200x630px** |
+| Same title/description on all pages | Google treats as duplicate content | Unique title (50-60 chars) + description (150-160 chars) per page |
+| Missing `og:type` | Defaults to "website" for articles | Set `article` for posts, `product` for products |
+
+### Technical
+
+| Gotcha | Why It Hurts | Fix |
+|--------|-------------|-----|
+| `robots.txt` blocks important pages | Pages not indexed | `Allow: /` for public, only block `/api/`, `/admin/` |
+| No sitemap or stale sitemap | Crawler misses new pages | Auto-generate, include `<lastmod>` with real dates |
+| `noindex` left in production | Entire site invisible | Verify `<meta name="robots">` in production build |
+| Images without `width`/`height` | CLS layout shift penalty | Always set dimensions + `loading="lazy"` for below-fold |
+
+### Core Web Vitals
+
+| Metric | Target | Common Miss |
+|--------|--------|-------------|
+| LCP | ≤2.5s | Hero image not preloaded — add `<link rel="preload">` |
+| INP | ≤200ms | Heavy JS on interaction — defer non-critical scripts |
+| CLS | ≤0.1 | Dynamic content without reserved space — set `min-height` |
+
+### Structured Data
+
+| Gotcha | Fix |
+|--------|-----|
+| JSON-LD not validated | Test with Google Rich Results Test before deploy |
+| Wrong `@type` | `Product` for products, `Article` for posts, `FAQPage` for FAQs |
+| Missing `BreadcrumbList` | Add breadcrumb schema for all non-root pages |
+
+## Done Criteria (K4)
+
+- [ ] Every page has unique title, description, canonical URL
+- [ ] OG images are 1200x630px on all shareable pages
+- [ ] `robots.txt` and `sitemap.xml` present and correct
+- [ ] Structured data validates in Rich Results Test
+- [ ] Core Web Vitals green (LCP ≤2.5s, INP ≤200ms, CLS ≤0.1)
+- [ ] No `noindex` tags in production

package/skills/techdebt/SKILL.md

@@ -1,122 +1,122 @@
----
-name: techdebt
-description: "Technical debt cleanup — detect and fix duplicate code, console.log, unused imports, any types, etc. Recommended before session end. Activates on techdebt, cleanup, debt keywords."
-triggers: [techdebt, cleanup, debt, unused imports, console.log, dead code]
-priority: 60
----
-
-# Techdebt — Technical Debt Cleanup
-
-Detect and clean up technical debt in the codebase before session end or periodically.
-
-## Inspection Items
-
-### 1. Duplicate Code
-
-- Check for similar functions/logic across multiple files
-- Identify code extractable into common utilities
-- Method: Detect similar code with `core_analyze_complexity`
-
-### 2. Unused Code
-
-- Unused import statements
-- Unused variables/functions
-- Commented-out code blocks
-
-Detection tools:
-
-```
-# Detect unused imports (using Grep tool)
-Grep: pattern="^import .+ from" → cross-reference usage
-
-# Detect commented-out code blocks
-Grep: pattern="^\\s*//.*\\b(function|const|let|var|class|import)\\b"
-```
-
-### 3. Debug Code
-
-- `console.log` / `console.error` / `console.warn`
-- `debugger` statements
-- Temporary comments: `// TODO`, `// FIXME`, `// HACK`, `// XXX`
-
-Detection tools:
-
-```
-# Detect console statements (using Grep tool)
-Grep: pattern="console\\.(log|error|warn|debug)" glob="*.{ts,tsx}"
-
-# Detect TODO/FIXME
-Grep: pattern="(TODO|FIXME|HACK|XXX)" glob="*.{ts,tsx}"
-
-# Detect debugger statements
-Grep: pattern="\\bdebugger\\b" glob="*.{ts,tsx}"
-```
-
-### 4. Code Quality
-
-- `any` type usage (TypeScript)
-- Hardcoded values (magic numbers/strings)
-- Functions exceeding 50 lines
-- Nesting deeper than 4 levels
-
-Detection tools:
-
-```
-# Detect any types (using Grep tool)
-Grep: pattern=": any\\b|as any\\b" glob="*.{ts,tsx}"
-
-# Analyze complexity with built-in VIBE tools
-core_analyze_complexity: filePath="src/**/*.ts"
-core_validate_code_quality: filePath="src/**/*.ts"
-```
-
-## Output Format
-
-```markdown
-## Technical Debt Report
-
-### Duplicate Code (N items)
-- src/utils.ts:formatDate ↔ src/helpers.ts:formatDateTime
-
-### Unused Imports (N items)
-- src/components/Button.tsx:3 — React (unused)
-
-### Debug Code (N items)
-- src/api/auth.ts:23 — console.log
-
-### Code Quality Issues (N items)
-- src/services/user.ts:45 — any type usage
-- src/utils/calc.ts:10 — magic number (hardcoded 365)
-
-Total: N technical debt items found.
-```
-
-## Auto-fix Scope
-
-### Auto-fixable (Safe)
-
-| Item | Fix Method |
-|------|-----------|
-| Unused imports | Delete the import statement |
-| `console.log` / `debugger` | Delete the line |
-| Trailing whitespace / blank lines | Apply formatter |
-
-### Requires Manual Review (Safety Guard)
-
-| Item | Reason |
-|------|--------|
-| Duplicate code extraction | Need to verify logic equivalence |
-| `any` type fixes | Need proper type design |
-| Magic number extraction | Need to decide constant names and locations |
-| Long function splitting | Need to decide logic separation criteria |
-
-> Always show the scope of changes to the user and get confirmation before auto-fixing.
-
-## VIBE Tool Integration
-
-| Tool | Purpose |
-|------|---------|
-| `core_analyze_complexity` | Measure function complexity (nesting, line count) |
-| `core_validate_code_quality` | Detect code quality rule violations |
-| `core_suggest_improvements` | Generate improvement suggestions |
-| `core_check_coupling_cohesion` | Analyze module coupling/cohesion |
+---
+name: techdebt
+description: "Technical debt cleanup — detect and fix duplicate code, console.log, unused imports, any types, etc. Recommended before session end. Activates on techdebt, cleanup, debt keywords."
+triggers: [techdebt, cleanup, debt, unused imports, console.log, dead code]
+priority: 60
+---
+
+# Techdebt — Technical Debt Cleanup
+
+Detect and clean up technical debt in the codebase before session end or periodically.
+
+## Inspection Items
+
+### 1. Duplicate Code
+
+- Check for similar functions/logic across multiple files
+- Identify code extractable into common utilities
+- Method: Detect similar code with `core_analyze_complexity`
+
+### 2. Unused Code
+
+- Unused import statements
+- Unused variables/functions
+- Commented-out code blocks
+
+Detection tools:
+
+```
+# Detect unused imports (using Grep tool)
+Grep: pattern="^import .+ from" → cross-reference usage
+
+# Detect commented-out code blocks
+Grep: pattern="^\\s*//.*\\b(function|const|let|var|class|import)\\b"
+```
+
+### 3. Debug Code
+
+- `console.log` / `console.error` / `console.warn`
+- `debugger` statements
+- Temporary comments: `// TODO`, `// FIXME`, `// HACK`, `// XXX`
+
+Detection tools:
+
+```
+# Detect console statements (using Grep tool)
+Grep: pattern="console\\.(log|error|warn|debug)" glob="*.{ts,tsx}"
+
+# Detect TODO/FIXME
+Grep: pattern="(TODO|FIXME|HACK|XXX)" glob="*.{ts,tsx}"
+
+# Detect debugger statements
+Grep: pattern="\\bdebugger\\b" glob="*.{ts,tsx}"
+```
+
+### 4. Code Quality
+
+- `any` type usage (TypeScript)
+- Hardcoded values (magic numbers/strings)
+- Functions exceeding 50 lines
+- Nesting deeper than 4 levels
+
+Detection tools:
+
+```
+# Detect any types (using Grep tool)
+Grep: pattern=": any\\b|as any\\b" glob="*.{ts,tsx}"
+
+# Analyze complexity with built-in VIBE tools
+core_analyze_complexity: filePath="src/**/*.ts"
+core_validate_code_quality: filePath="src/**/*.ts"
+```
+
+## Output Format
+
+```markdown
+## Technical Debt Report
+
+### Duplicate Code (N items)
+- src/utils.ts:formatDate ↔ src/helpers.ts:formatDateTime
+
+### Unused Imports (N items)
+- src/components/Button.tsx:3 — React (unused)
+
+### Debug Code (N items)
+- src/api/auth.ts:23 — console.log
+
+### Code Quality Issues (N items)
+- src/services/user.ts:45 — any type usage
+- src/utils/calc.ts:10 — magic number (hardcoded 365)
+
+Total: N technical debt items found.
+```
+
+## Auto-fix Scope
+
+### Auto-fixable (Safe)
+
+| Item | Fix Method |
+|------|-----------|
+| Unused imports | Delete the import statement |
+| `console.log` / `debugger` | Delete the line |
+| Trailing whitespace / blank lines | Apply formatter |
+
+### Requires Manual Review (Safety Guard)
+
+| Item | Reason |
+|------|--------|
+| Duplicate code extraction | Need to verify logic equivalence |
+| `any` type fixes | Need proper type design |
+| Magic number extraction | Need to decide constant names and locations |
+| Long function splitting | Need to decide logic separation criteria |
+
+> Always show the scope of changes to the user and get confirmation before auto-fixing.
+
+## VIBE Tool Integration
+
+| Tool | Purpose |
+|------|---------|
+| `core_analyze_complexity` | Measure function complexity (nesting, line count) |
+| `core_validate_code_quality` | Detect code quality rule violations |
+| `core_suggest_improvements` | Generate improvement suggestions |
+| `core_check_coupling_cohesion` | Analyze module coupling/cohesion |

package/skills/tool-fallback/SKILL.md

@@ -1,103 +1,103 @@
----
-name: tool-fallback
-description: "Tool failure fallback strategies with circuit breaker. Auto-activates on API errors, search failures, timeouts, 429, 5xx, overloaded errors."
-triggers: [API error, search failure, timeout, 429, 5xx, overloaded, fallback, circuit breaker]
-priority: 80
----
-
-# Tool Fallback Strategies
-
-## Pre-check (K1)
-
-> Did a tool just fail? If the error is a simple typo or wrong path, fix the input first. This skill is for persistent failures (429, 5xx, timeouts).
-
-## Circuit Breaker State Machine
-
-```
-┌─────────┐   3 failures   ┌─────────┐   30s cooldown   ┌─────────────┐
-│ CLOSED  │ ─────────────→ │  OPEN   │ ───────────────→ │ HALF-OPEN   │
-│ (normal)│                │ (block) │                  │ (test 1 req)│
-└─────────┘                └─────────┘                  └─────────────┘
-     ↑                                                        │
-     │                      success                           │
-     └────────────────────────────────────────────────────────┘
-```
-
-| State | Behavior |
-|-------|----------|
-| CLOSED | Normal operation, count failures |
-| OPEN | Skip tool immediately, use alternative |
-| HALF-OPEN | Allow 1 test request after cooldown |
-
-## Decision Trees
-
-### Web Search Fails
-
-```
-Web Search fails (429, 529, timeout)
-  → Check circuit state
-  → OPEN? → Skip to alternative immediately
-  → CLOSED? → Try context7 for library docs
-  → Still fails? → Claude's built-in knowledge (last resort)
-```
-
-### External LLM Fails
-
-```
-VibeOrchestrator.smartRoute({ type, prompt })
-  → Primary LLM fails (429, 401, 5xx)
-  → Skip to secondary LLM (no retry on rate limit)
-  → Secondary fails → Claude handles directly
-```
-
-### File/Code Not Found
-
-```
-Glob fails → Expand pattern: *.ts → **/*.ts → **/*
-  → Use Grep for content-based search
-  → Check git log for file history
-```
-
-## Error Response Actions
-
-| Error | Action | Circuit Impact |
-|-------|--------|---------------|
-| 429 Rate Limit | Skip to next alternative (don't retry) | +1 failure |
-| 5xx Server Error | Retry with backoff, then switch | +1 failure |
-| 529 Overloaded | Wait and retry once | +1 failure |
-| Timeout | Split request or retry | +1 failure |
-| 401/403 Auth | Re-auth or switch alternative | Don't count |
-
-## Retry Strategy
-
-```
-Request → Check circuit
-  ├─ OPEN → Use alternative immediately
-  └─ CLOSED/HALF-OPEN → Try request
-       ├─ Success → Reset failure count
-       └─ Fail → Backoff (2s → 4s → 8s)
-            └─ All retries failed → +1 failure
-                 └─ failures ≥ 3 → OPEN circuit (30s)
-                      └─ Use alternative
-```
-
-## LLM Priority by Task Type
-
-| Task Type | Primary → Secondary → Fallback |
-|-----------|-------------------------------|
-| architecture, debugging | GPT → Gemini → Claude |
-| uiux, code-analysis | Gemini → GPT → Claude |
-| code-gen, general | Claude only |
-
-## Principles
-
-1. **Never stop** — always find an alternative
-2. **Try before asking** — exhaust alternatives before asking user
-3. **Fail fast** — skip OPEN-circuit tools immediately
-4. **Auto-recover** — test after 30s cooldown
-
-## Done Criteria (K4)
-
-- [ ] Work continued despite tool failure
-- [ ] Alternative tool/method used successfully
-- [ ] No unnecessary retries on rate-limited tools
+---
+name: tool-fallback
+description: "Tool failure fallback strategies with circuit breaker. Auto-activates on API errors, search failures, timeouts, 429, 5xx, overloaded errors."
+triggers: [API error, search failure, timeout, 429, 5xx, overloaded, fallback, circuit breaker]
+priority: 80
+---
+
+# Tool Fallback Strategies
+
+## Pre-check (K1)
+
+> Did a tool just fail? If the error is a simple typo or wrong path, fix the input first. This skill is for persistent failures (429, 5xx, timeouts).
+
+## Circuit Breaker State Machine
+
+```
+┌─────────┐   3 failures   ┌─────────┐   30s cooldown   ┌─────────────┐
+│ CLOSED  │ ─────────────→ │  OPEN   │ ───────────────→ │ HALF-OPEN   │
+│ (normal)│                │ (block) │                  │ (test 1 req)│
+└─────────┘                └─────────┘                  └─────────────┘
+     ↑                                                        │
+     │                      success                           │
+     └────────────────────────────────────────────────────────┘
+```
+
+| State | Behavior |
+|-------|----------|
+| CLOSED | Normal operation, count failures |
+| OPEN | Skip tool immediately, use alternative |
+| HALF-OPEN | Allow 1 test request after cooldown |
+
+## Decision Trees
+
+### Web Search Fails
+
+```
+Web Search fails (429, 529, timeout)
+  → Check circuit state
+  → OPEN? → Skip to alternative immediately
+  → CLOSED? → Try context7 for library docs
+  → Still fails? → Claude's built-in knowledge (last resort)
+```
+
+### External LLM Fails
+
+```
+VibeOrchestrator.smartRoute({ type, prompt })
+  → Primary LLM fails (429, 401, 5xx)
+  → Skip to secondary LLM (no retry on rate limit)
+  → Secondary fails → Claude handles directly
+```
+
+### File/Code Not Found
+
+```
+Glob fails → Expand pattern: *.ts → **/*.ts → **/*
+  → Use Grep for content-based search
+  → Check git log for file history
+```
+
+## Error Response Actions
+
+| Error | Action | Circuit Impact |
+|-------|--------|---------------|
+| 429 Rate Limit | Skip to next alternative (don't retry) | +1 failure |
+| 5xx Server Error | Retry with backoff, then switch | +1 failure |
+| 529 Overloaded | Wait and retry once | +1 failure |
+| Timeout | Split request or retry | +1 failure |
+| 401/403 Auth | Re-auth or switch alternative | Don't count |
+
+## Retry Strategy
+
+```
+Request → Check circuit
+  ├─ OPEN → Use alternative immediately
+  └─ CLOSED/HALF-OPEN → Try request
+       ├─ Success → Reset failure count
+       └─ Fail → Backoff (2s → 4s → 8s)
+            └─ All retries failed → +1 failure
+                 └─ failures ≥ 3 → OPEN circuit (30s)
+                      └─ Use alternative
+```
+
+## LLM Priority by Task Type
+
+| Task Type | Primary → Secondary → Fallback |
+|-----------|-------------------------------|
+| architecture, debugging | GPT → Gemini → Claude |
+| uiux, code-analysis | Gemini → GPT → Claude |
+| code-gen, general | Claude only |
+
+## Principles
+
+1. **Never stop** — always find an alternative
+2. **Try before asking** — exhaust alternatives before asking user
+3. **Fail fast** — skip OPEN-circuit tools immediately
+4. **Auto-recover** — test after 30s cooldown
+
+## Done Criteria (K4)
+
+- [ ] Work continued despite tool failure
+- [ ] Alternative tool/method used successfully
+- [ ] No unnecessary retries on rate-limited tools